import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
import random

class Recommender:
    def __init__(self, retriever):
        self.curr_recommendations = []
        self.recommended = []
        self.retriever = retriever
        self.rand_seed = 5

    def _match_tags(self, material, interest):
        score = 0.7
        for tag in material['tags']:
            if cosine_similarity(np.array(self.retriever.encode([tag])),
                                 np.array(self.retriever.encode([interest]))) > score:
                if material not in self.curr_recommendations:
                    self.curr_recommendations.append(material)
                    self.recommended.append(False)

    def generate_recommendations(self, interests, new_material):
        for interest in interests:
            for material in new_material:
                self._match_tags(material, interest)

    def make_recommendation(self, user):
        if len(self.curr_recommendations) == 0:
            return ""
        index = random.choice(list(range(0, len(self.curr_recommendations))))
        while self.recommended[index] == True:
            index = random.choice(list(range(0, len(self.curr_recommendations))))
        recommendation = "Hey " + user + "! This " + self.curr_recommendations[index][
            'type'].lower() + " about " + ', '.join(
            self.curr_recommendations[index]['tags']).lower() + " was posted recently by " + \
                         self.curr_recommendations[index][
                             'author'].lower() + " on the catalogue. You may wanna check it out! It is titled " + \
                         self.curr_recommendations[index]['title'].lower() + ". Cheers, Janet"
        # self.curr_recommendations.remove(self.curr_recommendations[index])
        self.recommended[index] = True
        return recommendation